© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111189
    Prev
    Next
    INDEX
    Explanations

    zu Berlin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    {
    -3.08
    s
    -2.92
    d
    -2.84
    J
    -2.84
    lossians
    -2.84
    a
    -2.80
    on
    -2.61
    “
    -2.36
    able
    -2.30
     eds
    -2.25
    POSITIVE LOGITS
     của
    2.55
     ある
    2.47
    </td>
    2.42
    鹮
    2.31
     Of
    2.30
     چنین
    2.25
    Américaine
    2.19
     Vergnügen
    2.19
    ヱ
    2.16
    lindo
    2.03
    Activations Density 0.002%

    No Known Activations